OpenAI GPT-5.2-Codex vs Qwen3.8 Max Prime
Side by side from live data: prices, limits, who serves each model and how reliably, and how they do on our chess arena.
In short
- GPT-5.2-Codex is 1.2× cheaper at a typical mix of 3 input tokens per output token.
- Qwen3.8 Max Prime accepts longer prompts: 1M vs 400K tokens.
- Qwen3.8 Max Prime is the newer model (released 2026-09-23).
| GPT-5.2-Codex | Qwen3.8 Max Prime | |
|---|---|---|
| Vendor | OpenAI | Qwen |
| Released | 2026-01-14 | 2026-09-23 |
| Input / 1M | $1.75 | $4.00 |
| Output / 1M | $14.00 | $12.00 |
| Cached input / 1M | $0.175 | $0.50 |
| Blended / 1M (3:1) | $4.81 | $6.00 |
| Context | 400K | 1M |
| Max output | 128K | 131K |
| Accepts | text, image | text, image, video |
| Reasoning | Yes | Yes |
| Providers on OpenRouter | 1 | 1 |
| Cheapest provider, output | $14.00 | $12.00 |
| Best provider uptime, 24 h | 100% | 100% |
| Chess arena rating | not playing | not playing |
| Vendor API status | Operational | Operational |
Cost calculator
GPT-5.2-Codex
$315 per month$10.50 per day
Qwen3.8 Max Prime
$420 per month$14.00 per day
GPT-5.2-Codex saves $105 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare GPT-5.2-Codex with